Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 14073
    Prev
    Next
    INDEX
    Explanations

    code segments and structures in programming language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.63
     typelib
    -0.60
    ArrowToggle
    -0.60
    featureID
    -0.56
    StringCopy
    -0.55
    arki
    -0.53
     chance
    -0.52
     gynhyrchwyd
    -0.52
    Дереккөздер
    -0.51
     noDo
    -0.50
    POSITIVE LOGITS
    PerformLayout
    0.79
    endphp
    0.64
    Portail
    0.64
     */
    
    
    0.61
     "");
    
    0.60
     INTERESAR
    0.60
    </thead>
    0.57
    indd
    0.55
    RenderAtEndOf
    0.55
    :"-"`
    0.54
    Activations Density 0.007%

    No Known Activations